Skip to main content
The Meta Agent provides powerful capabilities that enable natural language interaction with the entire Kubiya platform.

​
Intelligent Task Routing

The Meta Agent understands your intent and routes requests to the appropriate resources: 
"Deploy the authentication service to staging"
The Meta Agent:
  1. Identifies the DevOps team/agent best suited for deployments
  2. Checks environment availability and worker capacity
  3. Creates and executes the task with proper context
  4. Streams results back to you

​
How Routing Works

Request TypeRouted To
Deployment tasksDevOps agents/teams
Security scansSecurity agents
Database operationsDBA agents
Infrastructure queriesContext Graph
Historical questionsCognitive Memory

​
Context Graph Exploration

The Meta Agent is your primary interface for exploring the Context Graph. Query your infrastructure without writing Cypher: 
"What services depend on the user-auth database?"
The Meta Agent:
  • Scans graph nodes for relevant entities
  • Traces relationships and dependencies
  • Returns structured, actionable results
  • Understands natural language queries about any ingested data

​
Example Queries

Query TypeExample
Dependencies”What depends on the payments service?”
Resource discovery”List all EC2 instances in production”
Permission analysis”Who has access to the customer-data S3 bucket?”
Relationship mapping”Show me the IAM roles attached to our Lambda functions”
Impact assessment”What would be affected if we deprecated the auth-v1 API?”
When to use Graph Explorer vs Meta Agent:
  • Use the Meta Agent for interactive exploration, asking questions, and getting insights
  • Use the Graph Explorer for visual analysis when you need to see the topology spatially

​
Cognitive Memory Access

Tap into organizational knowledge across all agents and teams: 
"What did we learn from the last production outage?"
The Meta Agent queries the cognitive memory system, which aggregates learnings from all agents operating in your environments.

​
Memory Use Cases

Use CaseExample Query
Incident history”What happened during similar incidents?”
Runbook lookup”Find the database failover runbook”
Decision context”Why did we choose Kubernetes?”
Best practices”What are our Python coding standards?”

​
Cross-Resource Coordination

Orchestrate complex operations spanning multiple platform resources: 
"Create a new project for Q1 cost optimization, assign the FinOps team,
and schedule weekly cloud spend analysis"
This single request triggers:
  • Project creation with defined goals
  • Team assignment with proper permissions
  • Background job scheduling with recurring execution

​
Multi-Step Operations

The Meta Agent can coordinate:
  1. Sequential tasks - Operations that must happen in order
  2. Parallel execution - Independent tasks running simultaneously
  3. Conditional logic - Different paths based on results
  4. Error handling - Graceful recovery from failures

​
Platform Management

​
Agent Operations

"List all agents that have shell access"
"Create a new agent for database migrations with PostgreSQL skills"
"Execute the DevOps agent to check Kubernetes cluster health"

​
Team Coordination

"Show me all teams and their member agents"
"Create a Platform Engineering team with DevOps and SRE agents"
"Which teams have access to the production environment?"

​
Environment Management

"List all environments and their configurations"
"Create a staging environment with limited AWS access"
"What secrets are available in the production environment?"

​
Execution Monitoring

"Show me all failed executions from the last 24 hours"
"What's the status of execution abc123?"
"Cancel all running executions for the backup agent"

​
Usage Patterns by Role

​
For Business Users

Ask questions without technical knowledge: 
"How many deployments happened this week?"
"What's the status of our cloud cost reduction project?"
"Show me any security issues that need attention"

​
For Developers

Interact with platform resources naturally: 
"List all agents that have shell access"
"Execute the DevOps agent to check our Kubernetes cluster health"
"Create an agent for database migrations with PostgreSQL skills"

​
For Data Engineers

Explore infrastructure relationships: 
"Map all data pipelines connected to the analytics warehouse"
"What resources are in our AWS us-east-1 region?"
"Show me the dependency tree for our ETL jobs"

​
For Platform Engineers

Coordinate and manage platform resources: 
"What workers are connected to the production queue?"
"Show me all failed executions from the last 24 hours"
"Which teams have access to the production environment?"

​
Understanding Responses

Meta Agent responses include:
  1. Reasoning Process - Transparent display of how the request was interpreted
  2. Tool Calls - Visual indicators showing which MCP tools were invoked
  3. Visual/JSON Toggle - Switch between formatted and raw data views
  4. Structured Results - Organized output with clear sections
  5. Recommendations - Actionable next steps based on findings
  6. Follow-up Options - Suggested queries to explore further

​
What’s Next